{"id":"https://openalex.org/W4412877075","doi":"https://doi.org/10.1145/3711896.3737066","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","display_name":"Offline Trajectory Optimization for Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877075","doi":"https://doi.org/10.1145/3711896.3737066"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737066","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100675787","display_name":"Ziqi Zhao","orcid":"https://orcid.org/0009-0008-3011-5745"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqi Zhao","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384130","display_name":"Zhaochun Ren","orcid":"https://orcid.org/0000-0002-9076-6565"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhaochun Ren","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101335048","display_name":"Liu Yang","orcid":"https://orcid.org/0009-0007-7508-0964"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Yang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067964547","display_name":"Yongli Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsen Liang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081665927","display_name":"Fajie Yuan","orcid":"https://orcid.org/0000-0001-8452-9929"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fajie Yuan","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046700486","display_name":"Pengjie Ren","orcid":"https://orcid.org/0000-0003-2964-6422"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Ren","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050947285","display_name":"Zhumin Chen","orcid":"https://orcid.org/0000-0003-4592-4074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhumin Chen","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113691072","display_name":"Jun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393241","display_name":"Xin Xin","orcid":"https://orcid.org/0000-0001-6116-9115"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xin","raw_affiliation_strings":["Shandong University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100675787"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09732036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4002","last_page":"4013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8283770084381104},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7332216501235962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7032161951065063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535686731338501},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5098899602890015},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5028755068778992},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4691675305366516},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.4399644732475281},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.2701886296272278},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1795334815979004},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05429553985595703}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8283770084381104},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7332216501235962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032161951065063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535686731338501},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5098899602890015},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5028755068778992},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691675305366516},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.4399644732475281},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2701886296272278},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1795334815979004},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05429553985595703},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737066","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6216555950","display_name":null,"funder_award_id":"T2293773","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6283261777","display_name":null,"funder_award_id":"62472261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8283770779","display_name":null,"funder_award_id":"62272274","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G83507391","display_name":null,"funder_award_id":"62202271","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877075.pdf","grobid_xml":"https://content.openalex.org/works/W4412877075.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1547925194","https://openalex.org/W3003609932","https://openalex.org/W3025019304","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3035564946","https://openalex.org/W3090369311","https://openalex.org/W3121045039","https://openalex.org/W3153007185","https://openalex.org/W3173984942","https://openalex.org/W3178225342","https://openalex.org/W4283205689","https://openalex.org/W4285604474","https://openalex.org/W4296604485","https://openalex.org/W6777656069"],"related_works":["https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2361427670","https://openalex.org/W2139910871","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"aims":[4],"to":[5,30,66],"learn":[6],"policies":[7],"without":[8],"online":[9],"explorations.":[10],"To":[11],"enlarge":[12],"the":[13,56],"training":[14],"data,":[15,64],"model-based":[16],"offline":[17,44],"RL":[18,45],"learns":[19],"a":[20,27],"dynamics":[21],"model":[22],"which":[23],"is":[24],"utilized":[25],"as":[26],"virtual":[28],"environment":[29],"generate":[31],"simulation":[32],"data":[33,40],"and":[34,54,60],"enhance":[35],"policy":[36],"learning.":[37],"However,":[38],"existing":[39],"augmentation":[41],"methods":[42],"for":[43,62],"suffer":[46],"from":[47,51],"(i)":[48],"trivial":[49],"improvement":[50],"short-horizon":[52],"simulation;":[53],"(ii)":[55],"lack":[57],"of":[58],"evaluation":[59],"correction":[61],"generated":[63],"leading":[65],"low-qualified":[67],"augmentation.":[68]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}